Difyapp As MCP Server

🚀 Expose Dify Workflows as an MCP Server

This project exposes Dify workflows as a server via the Model Context Protocol (MCP), making them accessible to AI clients such as Claude.

📋 Project Overview

This project implements a Dify plugin that allows Dify workflows to be exposed via the Model Context Protocol (MCP) to AI clients supporting this protocol (e.g., Claude Desktop, Cursor). With this plugin, you can:

• Provide Dify workflows as tools to AIs like Claude.
• Enable AI clients to discover and use your workflows.
• Integrate workflows into AI assistants without modifying them.

✨ Features

• ✅ Support for the JSON - RPC interface compliant with the MCP standard.
• ✅ Automatic discovery and registration of tools.
• ✅ Compatibility with clients such as Claude Desktop and Cursor.
• ✅ Secure implementation of SSE connections.
• ✅ Server - side session management.
• 🔄 Compliance with the latest MCP Streamable HTTP specification (based on PR #206).

📚 Background

The Model Context Protocol (MCP) is an open standard that enables AI models to interact with external tools and data sources. As MCP evolves, the protocol is transitioning from the HTTP + SSE mode to the new "Streamable HTTP" transport mode, offering better support for stateless servers.

This project tracks and implements the latest changes in the MCP protocol, specifically:

• The server is responsible for generating and managing session IDs.
• Support for the stateless server mode (suitable for the Dify plugin environment).
• Standardized message formats and stream processing.
• Secure session management and authentication.

🛠️ Configure Plugin Settings

1. Plugin Configuration

After installing and enabling the MCP Server plugin in Dify, you need to make the following configurations:

• Application ID: The ID of the Dify application you want to expose.
• Other Settings: Configure as needed.

💻 Usage Examples

1. Configure in Dify

Ensure that your Dify application contains at least one workflow and is correctly configured.

2. Use in Clients

1. Open the client.
2. Go to Settings > MCP Server.
3. Add a new MCP server and fill in the URL:

   https://your-dify-instance-address/difyapp_as_mcp_server
   

4. Save and enable the server.

3. Use in Cursor

1. Open Cursor.
2. Go to Settings > AI > MCP.
3. Add the server address:

   https://your-dify-instance-address/difyapp_as_mcp_server
   

4. Save and enable.
5. Use the plugin in Cursor.

🔧 Technical Details

1. Implementation Overview

• Server Endpoint: Provides a JSON - RPC interface supporting the MCP protocol.
• Tool Registration: Automatically discovers and registers Dify workflows as available tools.
• Stateless Mode: Supports a lightweight, stateless communication method.
• Session Management: Implements server - side session management to ensure secure connections.

🐞 Troubleshooting

1. Common Issues

• Unable to connect to the MCP server:
  • Check the network connection.
  • Ensure the server address is correct.
  • Ensure the server is enabled.
• Tools are not discovered:
  • Check if the plugin is enabled.
  • Ensure the application ID is correctly configured.
  • Restart the Dify service.

🤝 Contribution

Contributions to the code and documentation are welcome to help improve the MCP Server plugin.

📄 License

This project is licensed under the [License Name] license. Please refer to the LICENSE file in the project repository for detailed information.

🙏 Acknowledgments

Thanks to the support of the community and the efforts of contributors, this project has been realized.